Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/21102#discussion_r207781744
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -3965,6 +4034,248 @@ object ArrayUnion {
}
}
+/**
+ * Returns an array of the elements in the intersect of x and y, without
duplicates
+ */
+@ExpressionDescription(
+ usage = """
+ _FUNC_(array1, array2) - Returns an array of the elements in the
intersection of array1 and
+ array2, without duplicates.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3), array(1, 3, 5));
+ array(1, 3)
+ """,
+ since = "2.4.0")
+case class ArrayIntersect(left: Expression, right: Expression) extends
ArraySetLike
+ with ComplexTypeMergingExpression {
+ override def dataType: DataType = {
+ dataTypeCheck
+ ArrayType(elementType,
+ left.dataType.asInstanceOf[ArrayType].containsNull &&
+ right.dataType.asInstanceOf[ArrayType].containsNull)
+ }
+
+ @transient lazy val evalIntersect: (ArrayData, ArrayData) => ArrayData =
{
+ if (elementTypeSupportEquals) {
+ (array1, array2) =>
+ if (array1.numElements() != 0 && array2.numElements() != 0) {
+ val hs = new OpenHashSet[Any]
+ val hsResult = new OpenHashSet[Any]
+ var foundNullElement = false
+ var i = 0
+ while (i < array2.numElements()) {
+ if (array2.isNullAt(i)) {
+ foundNullElement = true
+ } else {
+ val elem = array2.get(i, elementType)
+ hs.add(elem)
+ }
+ i += 1
+ }
+ val arrayBuffer = new scala.collection.mutable.ArrayBuffer[Any]
+ i = 0
+ while (i < array1.numElements()) {
+ if (array1.isNullAt(i)) {
+ if (foundNullElement) {
+ arrayBuffer += null
+ foundNullElement = false
+ }
+ } else {
+ val elem = array1.get(i, elementType)
+ if (hs.contains(elem) && !hsResult.contains(elem)) {
+ arrayBuffer += elem
+ hsResult.add(elem)
+ }
+ }
+ i += 1
+ }
+ new GenericArrayData(arrayBuffer)
+ } else {
+ new GenericArrayData(Seq.empty)
--- End diff --
nit: `Array.empty` or `Array.emptyObjectArray`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
